Assessing exterior egg quality indicators using machine vision

Abstract

1. The objective of this study was to develop a machine vision method for analysing exterior parameters of chicken eggs to automate the stage of primary sorting. 2. The developed algorithm based on predetermined thresholds calculated egg quality indicators, including geometric dimensions, shape index and the mottling grade. The algorithm was implemented with an experimental setup that combined the image-based and the candling methods. A total of 400 egg samples were analysed. 3. Comparison of results of the algorithm with those obtained using the traditional manual method showed that mean value of radii values difference was 0.095 ± 0.058 mm for the sharp and 0.080 ± 0.047 mm for the blunt end of the egg, with standard deviations of 0.58 mm and 0.49 mm, respectively. 4. The correlation coefficient between the shape index values determined by the two methods was 0.93; the standard deviation of absolute differences between corresponding values was 1.05%. 5. The results of mottling grade estimation were compared using F-measure and confusion matrix. 6. The results allow the possibility to perform the assessment of egg exterior quality factors in an automatic mode, independent of the expertise of a grader.

Application of Classification Techniques in the Analysis of External Characteristics of Eggs

“…A number of methods that are efficient in their classification accuracy, such as the Support vector machines Method, Neural Networks, Genetic Algorithms, have been used to process data from these sensors. The prediction and classification of eggs, depending on their weight, whether using regression methods or complex computational procedures, is of close accuracy [28,33]. There is an obvious need to look for effective, rapid and simplified classification approaches, methods and tools for an automated, objective and sufficiently accurate assessment of key egg indicators [16].…”

A non-contact measuring device for determining poultry eggs weight

“…In the production of eggs, the main studies on the prediction of egg weight are directed in relation to their sorting, incubation, packaging (Kokoszyński et al, 2013). The refinement of different methods of measuring and indirectly determining eggs weight is a major topic in available research (Aragua and Mabayo 2018;Vasileva et al, 2018). In recent years, machine vision techniques have been used to predict the eggs weight for sorting purposes (Alikhanov et al, 2017).…”